commit f3a628fe3bb578d97850a30c63eba09f427fb40a Author: ModelHub XC Date: Tue Sep 8 14:36:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5febb22 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Law-Memory-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MemSFT-Qwen3-Law-Memory-8B.IQ4_XS.gguf b/MemSFT-Qwen3-Law-Memory-8B.IQ4_XS.gguf new file mode 100644 index 0000000..05b4400 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b2cc9992730e359e016cae1d5179ec7ade61cd8a1b41a2e4daa009ba287384 +size 4591812992 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q2_K.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q2_K.gguf new file mode 100644 index 0000000..ec8b910 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb0e10556444bae0359de3866b40f595cb332f8eb35367121e0d3734b95fdfa +size 3280471360 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q3_K_L.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0da4583 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81009213c65595340836030b27824e4e57d847a4f17a95fad3b5b06d2753437b +size 4430021472 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q3_K_M.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q3_K_M.gguf new file mode 100644 index 0000000..d5067ea --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e227dea2c8beae89a91616c362aa70ff03d04752db83ade544c2f0ec229450 +size 4122788704 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q3_K_S.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q3_K_S.gguf new file mode 100644 index 0000000..d22ccc1 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d627993605055133b85ec89140d0cb789036e9fc164e4bdee4ced00facdd67 +size 3768238944 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q4_K_M.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q4_K_M.gguf new file mode 100644 index 0000000..d45062d --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:030e7b2f79e9f307e3a77c0d3e0d361ebeede2afce63bd446e810dc691e03a6e +size 5026266112 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q4_K_S.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q4_K_S.gguf new file mode 100644 index 0000000..e1064a0 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5302fde778095c405a34835a20517db8738009e3f95523f33b7034612ada7141 +size 4800494592 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q5_K_M.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q5_K_M.gguf new file mode 100644 index 0000000..13426aa --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ec0dcc97b6898ddb52df0762e3687b94df32e4b6982e881ed3a636f159c975 +size 5849458176 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q5_K_S.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q5_K_S.gguf new file mode 100644 index 0000000..fc675ab --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056e6b753f810f2dc8b688b87f2fab602448595038e2d101d8a4e65eb407d7f1 +size 5719107072 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q6_K.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q6_K.gguf new file mode 100644 index 0000000..729ebc2 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a29c533784941ca63dc7f1b1636d8838a84ca760c17cb0c595591e1ed8a5481 +size 6724099744 diff --git a/MemSFT-Qwen3-Law-Memory-8B.Q8_0.gguf b/MemSFT-Qwen3-Law-Memory-8B.Q8_0.gguf new file mode 100644 index 0000000..6e0da46 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f162daf455f25cc8f708813efb89430ffcaa31a5f22fdbf3c3b7f1fba59b2a +size 8707189088 diff --git a/MemSFT-Qwen3-Law-Memory-8B.f16.gguf b/MemSFT-Qwen3-Law-Memory-8B.f16.gguf new file mode 100644 index 0000000..ab68784 --- /dev/null +++ b/MemSFT-Qwen3-Law-Memory-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d189eaabde3bd2076c77199e689be3018afcc661ce0b6e3ac07fe9f1799edbc +size 16383663968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ee9f712 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Jiarui-Wang/MemSFT-Qwen3-Law-Memory-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- memsft +- memory-decoder +- law +- legal-domain +- lawbench +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jiarui-Wang/MemSFT-Qwen3-Law-Memory-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MemSFT-Qwen3-Law-Memory-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Law-Memory-8B-GGUF/resolve/main/MemSFT-Qwen3-Law-Memory-8B.f16.gguf) | f16 | 16.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +